{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mm-eval-a-multilingual-meta-evaluation","title":"MM-Eval: A Multilingual Meta-Evaluation Benchmark for LLM-as-a-Judge and Reward Models","arxiv_id":"2410.17578","date":"2024-10-23","proceeding":null,"authors":["Guijin Son","Dongkeun Yoon","Juyoung Suk","Javier Aula-Blasco","Mano Aslan","Vu Trong Kim","Shayekh Bin Islam","Jaume Prats-Cristià","Lucía Tormo-Bañuelos","Seungone Kim"],"abstract":"As Large Language Models (LLMs) are now capable of producing fluent and coherent content in languages other than English, it is not imperative to precisely evaluate these non-English outputs. However, when assessing the outputs from mutlilingual LLMs, prior works often employed LLM based evaluators that excel at assessing English outputs, without a thorough examination of whether these evaluators could effectively assess non-English text as well. Moreover, existing benchmarks to test evaluator LLMs (referred to as \"meta-evaluation benchmarks\") are mostly English-centric. To bridge this gap and examine whether evaluator LLMs can reliably assess the outputs of multilingual LLMs, we introduce MM-Eval, a multilingual meta-evaluation benchmark comprising five core subsets covering 18 languages and a Language Consistency subset spanning 122 languages. A core attribute of MM-Eval is that, instead of merely translating existing English meta-evaluation benchmarks, it is designed with multilingual-specific challenges in mind. Additionally, unlike existing meta-evaluation benchmarks that focus solely on ranking accuracy over pairwise data, MM-Eval also evaluates the consistency and fairness of absolute score values across a wide range of languages. Our results show that existing evaluator LLMs that excel in English contexts have considerable room for improvement when assessing non-English outputs. Furthermore, we find that evaluators are unfair and inconsistent when evaluating lower-resourced languages. Finally, we validate MM-Eval by measuring its correlation with Best-of-N rankings, finding a significantly stronger correlation compared to other meta-evaluation benchmarks. We publicly release our benchmark and code.","url_abs":"https://arxiv.org/abs/2410.17578v2","url_pdf":"https://arxiv.org/pdf/2410.17578v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mm-eval-a-multilingual-meta-evaluation","repo_url":"https://github.com/guijinSON/MM-Eval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"fairness","task_name":"Fairness"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2410.17578","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17578"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/guijinSON/MM-Eval","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"ecef5c1b4b23a359","entry":"format_judge_answers","repo":"guijinSON/MM-Eval","repo_kind":"official","path":"rewardbench/generative.py","file_url":"https://github.com/guijinSON/MM-Eval/blob/HEAD/rewardbench/generative.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ecef5c1b4b23a359"}},{"code_sha256_prefix":"39e3cf1d3ab26978","entry":"pad_to_length","repo":"guijinSON/MM-Eval","repo_kind":"official","path":"rewardbench/dpo.py","file_url":"https://github.com/guijinSON/MM-Eval/blob/HEAD/rewardbench/dpo.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"39e3cf1d3ab26978"}},{"code_sha256_prefix":"561f4fef3d5dd177","entry":"process_judgement","repo":"guijinSON/MM-Eval","repo_kind":"official","path":"rewardbench/generative.py","file_url":"https://github.com/guijinSON/MM-Eval/blob/HEAD/rewardbench/generative.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"561f4fef3d5dd177"}},{"code_sha256_prefix":"00b839c7c0ba9d17","entry":"tokenize_conv_pair","repo":"guijinSON/MM-Eval","repo_kind":"official","path":"rewardbench/models/betterpairrm.py","file_url":"https://github.com/guijinSON/MM-Eval/blob/HEAD/rewardbench/models/betterpairrm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"00b839c7c0ba9d17"}},{"code_sha256_prefix":"a7144f10a520a12d","entry":"tokenize_pair","repo":"guijinSON/MM-Eval","repo_kind":"official","path":"rewardbench/models/betterpairrm.py","file_url":"https://github.com/guijinSON/MM-Eval/blob/HEAD/rewardbench/models/betterpairrm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a7144f10a520a12d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}